{"id":"W2808007596","doi":"10.65109/miek6215","title":"Training Dialogue Systems With Human Advice","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Microsoft (Canada)","funders":"Horizon 2020 Framework Programme; European Commission","keywords":"Reinforcement learning; Computer science; Perspective (graphical); Bridge (graph theory); Encoding (memory); Point (geometry); Reinforcement; Artificial intelligence; Advice (programming); Human–computer interaction; Engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006528797,0.0004142529,0.0005970938,0.0002100884,0.0001937547,0.0008493781,0.0021589,0.0003457007,0.00001568301],"category_scores_gemma":[0.00002478051,0.0003106646,0.0001112499,0.0002388956,0.00009726883,0.0002311691,0.001097797,0.0004135331,0.0002955782],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008846539,"about_ca_system_score_gemma":0.0003865858,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002859335,"about_ca_topic_score_gemma":0.0004581216,"domain_scores_codex":[0.9971898,0.0001665868,0.0004742187,0.001057792,0.0005562751,0.0005553952],"domain_scores_gemma":[0.9973246,0.00007481268,0.0003307834,0.001776722,0.0002431882,0.0002498304],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001394582,0.0006977688,0.005994569,0.0037041,0.001922597,0.00138784,0.04946283,0.006471193,0.001364901,0.7196353,0.1831477,0.02607171],"study_design_scores_gemma":[0.01432609,0.008860688,0.01920112,0.01657181,0.0006914465,0.003445482,0.008483293,0.4221361,0.004570713,0.09077136,0.3855663,0.02537563],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01087352,0.0003616123,0.6041857,0.0001749187,0.007158177,0.001210462,0.00002608951,0.002513777,0.3734957],"genre_scores_gemma":[0.9737846,0.000004106845,0.02124806,0.0001672352,0.001883966,0.0001632619,0.00006884758,0.00003847487,0.00264141],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9629111,"threshold_uncertainty_score":0.9999346,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05333686751493118,"score_gpt":0.2733405274845878,"score_spread":0.2200036599696566,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}